MLKitPoseDetectionCommon 框架参考
使用集合让一切井井有条
根据您的偏好保存内容并对其进行分类。
MLKPoseLandmark
@interface MLKPoseLandmark : NSObject
姿势检测结果中的特征点。
-
-
3D 点在输入图像空间中的位置。
Z 值在图片空间中没有固定的原点。而 Z 轴原点位于
臀部。Z 值为负表示地标位于
z-origin,在检测到的人物和相机之间。而 z 值为正值表示
该地标位于 z 原点后面。
Z 值没有固定的范围。不过,由于 z 坐标系包含在输入中,
z 值可用于推断地标之间的相对距离,测量位置
图片像素。
注意:Z 值的准确性低于 x 值和 y 值。此外,面部特征点的 Z 值
不会计算,因此请忽略它们。
声明
Objective-C
@property (nonatomic, readonly) MLKVision3DPoint *_Nonnull position;
-
特征点实际位于图片帧中的可能性(范围为 [0, 1])。
声明
Objective-C
@property (nonatomic, readonly) float inFrameLikelihood;
-
声明
Objective-C
- (nonnull instancetype)init;
如未另行说明,那么本页面中的内容已根据知识共享署名 4.0 许可获得了许可,并且代码示例已根据 Apache 2.0 许可获得了许可。有关详情,请参阅 Google 开发者网站政策。Java 是 Oracle 和/或其关联公司的注册商标。
最后更新时间 (UTC):2025-07-25。
[null,null,["最后更新时间 (UTC):2025-07-25。"],[[["\u003cp\u003e\u003ccode\u003eMLKPoseLandmark\u003c/code\u003e represents a specific point on a detected body within an image.\u003c/p\u003e\n"],["\u003cp\u003eEach landmark includes its type (body location), 3D position in the image, and a likelihood of being within the frame.\u003c/p\u003e\n"],["\u003cp\u003eThe 3D position's z-value indicates relative depth, with negative values closer to the camera and positive values further away, relative to the person's hip.\u003c/p\u003e\n"],["\u003cp\u003eWhile the z-values help understand relative depth, they are less accurate than the x and y coordinates and are not calculated for facial landmarks.\u003c/p\u003e\n"]]],["MLKPoseLandmark represents a body landmark in pose detection. It provides the `type`, indicating the body location, and the `position`, a 3D point in image space with z-origin at the hip. The `inFrameLikelihood` property, ranging from 0 to 1, reflects the confidence of the landmark's presence in the image. Z-values indicate depth relative to the hip, with negative values in front and positive values behind. Facial landmarks do not have z-values. The init method is unavailable.\n"],null,["# MLKitPoseDetectionCommon Framework Reference\n\nMLKPoseLandmark\n===============\n\n\n @interface MLKPoseLandmark : NSObject\n\nA landmark in a pose detection result.\n- `\n ``\n ``\n `\n\n ### [type](#/c:objc(cs)MLKPoseLandmark(py)type)\n\n `\n ` \n The landmark type (i.e. location on the body). \n\n #### Declaration\n\n Objective-C \n\n @property (nonatomic, readonly) ../Type-Definitions.html#/c:MLKPoseLandmark.h@T@MLKPoseLandmarkType _Nonnull type;\n\n- `\n ``\n ``\n `\n\n ### [position](#/c:objc(cs)MLKPoseLandmark(py)position)\n\n `\n ` \n The position of the 3D point in the input image space.\n\n The z-value does not have a fixed origin in the image space. Instead, the z-origin is located on\n the detected person's hip. A negative z-value indicates that the landmark is in front of the\n z-origin, between the detected person and the camera. Whereas a positive z-value indicates that\n the landmark is behind the z-origin.\n\n Z-values don't have a fixed range. However, since the z-coordinate system is in the input\n image space, the z-values can be used to infer relative distance between landmarks, measured in\n image pixels.\n\n Note: Z-values are less accurate than x and y-values. Additionally, z-values for facial landmarks\n are not calculated, so please disregard them. \n\n #### Declaration\n\n Objective-C \n\n @property (nonatomic, readonly) MLKVision3DPoint *_Nonnull position;\n\n- `\n ``\n ``\n `\n\n ### [inFrameLikelihood](#/c:objc(cs)MLKPoseLandmark(py)inFrameLikelihood)\n\n `\n ` \n The likelihood, in range \\[0, 1\\], that the landmark is actually in the image frame. \n\n #### Declaration\n\n Objective-C \n\n @property (nonatomic, readonly) float inFrameLikelihood;\n\n- `\n ``\n ``\n `\n\n ### [-init](#/c:objc(cs)MLKPoseLandmark(im)init)\n\n `\n ` \n Unavailable. \n\n #### Declaration\n\n Objective-C \n\n - (nonnull instancetype)init;"]]